eval-harnessskills.sh · affaan-m
10,071 installsEval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, grade with code-based, model-based, rule, or human graders, and track pass@k and pass^k reliability. Use when defining pass/fail criteria for agent tasks, measuring agent reliability, building regression suites for prompt or agent changes, or benchmarking across model versions.
Evidence lines
- executes_fetched_code — SKILL.md: name: eval-harness
- executes_fetched_code — SKILL.md: description: Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, grade with code-based, model
- executes_fetched_code — SKILL.md: # Eval Harness Skill
- executes_fetched_code — SKILL.md: A formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles.
- executes_fetched_code — SKILL.md: - Setting up eval-driven development (EDD) for AI-assisted workflows
Our disclosure is a static description of what the skill declares and does; it is not a safety verdict. Source record: www.skills.sh/affaan-m/ecc/eval-harness.
Install
npx skills add affaan-m/ecc@eval-harness
Copied from the registry's documented install form. Read the disclosure above first; it is the whole point of this page.
Observed record
2 weekly observations since 2026-09-28. Installs 9905 → 10071.
The skill's content hash has not changed while we watched.
Cite this page
Sato Hub. "eval-harness — skill disclosure on Sato Hub." Sato Hub, updated 2026-10-23, accessed 2026-10-23. https://satohub.ai/skills/skillssh%3Aaffaan-m%2Fecc%2Feval-harnessData last refreshed 2026-10-23; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.